mdvs: Agent for Claude Code

.claude/agents/ship-reviewer.md

ship-reviewer is an agent for Claude Code from edochi/mdvs. It costs 51 tokens per session (453 once invoked), scanned A, original, MIT.

A read-only reviewer that attacks one proposed code change from a chosen angle, such as correctness, API boundaries, test quality, or simplicity. It requires concrete failure scenarios and evidence from the actual files.

In plain words
What is it for?
Use it to review a change for specific inputs, ordering, or state that could make it fail. It can also check whether existing language features or libraries make custom code unnecessary.
Why use it?
It helps expose bugs and unnecessary complexity that a normal review may miss, without modifying the source tree or Git history.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; names the NotebookEdit tool; mentions AGENTS.md.

This is edochi/mdvs's own configuration. It tells Claude Code how to work on mdvs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mdvs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to edochi/mdvs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/edochi/mdvs/main/.claude/agents/ship-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/edochi/mdvs

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ship-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/edochi/mdvs/ship-reviewer/github.svg)](https://agentmods.dev/agents/edochi/mdvs/ship-reviewer)
Your own site
<a href="https://agentmods.dev/agents/edochi/mdvs/ship-reviewer"><img src="https://agentmods.dev/badge/agents/edochi/mdvs/ship-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ship-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/edochi/mdvs/ship-reviewer"><img src="https://agentmods.dev/badge/agents/edochi/mdvs/ship-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 453 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.00453
Opus 5.5 $0.00020 $0.00181
Sonnet 5.5 $0.00010 $0.00091
Haiku 4.5 $0.00005 $0.00045

Measured 10d ago against content hash f6c872913f0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ship-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/ship-reviewer.md · 41 lines

What it actually says

You review one change through the single lens your dispatch names. Attack it: find the input, ordering, or state under which it is wrong, and show the trace. A finding without a concrete failure scenario is not a finding.

Verify every claim against the real file before reporting it, and cite file and symbol. Rank findings by severity; say plainly which ones you are confident in and which are plausible but unconfirmed.

You are read-only. No file writes, no probe files, no git mutation (checkout, reset, stash, clean, restore, staging, committing). If you need to execute code to confirm a finding, say so and stop; the coordinator will give you a worktree.

When resumed to re-review, check only whether each of your prior findings was addressed, and say which remain open.

The simplicity/idiom lens asks whether the change is the least code that does the job: which abstraction is not earning its place (a mirror struct, a per-call parser, a hand-written mapping, a duplicated helper), what a senior Rust reviewer would delete, and where serde, the type system or the standard library already do the work the code does by hand. It also flags every magic number: a bare numeric literal carrying meaning in production or test code where a named constant or a typed ecosystem value belongs. The layering/API lens checks the architectural invariants in AGENTS.md: enum dispatch with exhaustive matches, validation standing alone without the embedding model, coercion living in the preprocessor pipeline rather than the schema. A precedent elsewhere in the tree is not a defence; judge the precedent too, and say when the pattern being copied is the smell.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 41 lines · 51 tokens per session scan A f6c872913f0c

Subscribe to this mod's changes

ship-reviewer is an agent published in the GitHub repository edochi/mdvs (27 stars, last pushed 11d ago), licensed MIT. It adds 51 tokens to every session and 453 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-05.

Related

Other agents, from other repositories

lint-rule-handler

Map a natural-language wiki-health request to one or more scraps lint rules, run them, interpret each violation as a signal against the user's purpose, and either apply mechanical fixes or report findings. Use this agent for purpose-driven Scraps lint work.

boykush/scraps · 53 tokens

symbol-analyst

Wave 2 agent: performs deep analysis of critical and important symbols. Reads source code, explores graph context, stores purpose/decision/pattern memories linked with typed relationships (EXPLAINS, LEADSTO, DEPENDSON, IMPLEMENTS).

cogniplex/codemem · 54 tokens

architecture-reviewer

Wave 3 agent: analyzes module boundaries, dependency patterns, and layering decisions across the entire codebase. Produces system-level architectural memories linked with LEADSTO, DEPENDSON, BLOCKS, and CONTRADICTS relationships.

cogniplex/codemem · 51 tokens

pattern-hunter

Wave 2 agent: discovers cross-file patterns within Louvain clusters. Identifies naming conventions, shared structures, and recurring approaches. Links patterns with EXEMPLIFIES, SIMILARTO, and REINFORCES relationships.

cogniplex/codemem · 49 tokens

security-reviewer

Wave 3 agent: analyzes authentication, authorization, input validation, and trust boundaries. Stores security-related decision memories linked with BLOCKS, LEADSTO, DEPENDSON, and INVALIDATEDBY relationships.

cogniplex/codemem · 45 tokens

Smart Exclude

Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.

agentgg-dev/agentgg · 36 tokens